Drop messages from the input array until the total is under maxTokens. Three strategies: drop-oldest (default), drop-middle, priority (uses each message's `priority` field). Always returns a structured result with token counts before and after; never throws across the wire.
Accepts raw HTML/template content (messages[].content); High parameter count (11 properties)
Part of the Agentfit MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call fit_messages to permanently remove or destroy resources in Agentfit. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call fit_messages in a loop, permanently destroying resources in Agentfit. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
fit_messages:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Agentfit policy for all 3 tools.
Agents calling destructive-class tools like fit_messages have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
fit_messages is one of the critical-risk operations in Agentfit. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Drop messages from the input array until the total is under maxTokens. Three strategies: drop-oldest (default), drop-middle, priority (uses each message's `priority` field). Always returns a structured result with token counts before and after; never throws across the wire.. It is categorised as a Destructive tool in the Agentfit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for fit_messages. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agentfit MCP server.
fit_messages is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the fit_messages rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for fit_messages. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fit_messages is provided by the Agentfit MCP server (@mukundakatta/agentfit-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.